Beyond Compression: A Comprehensive Evaluation of Lossless Floating-Point Compression

Summary: Comprehensive empirical evaluation of lossless floating-point compressors for columnar engines, measuring compression ratio, in-situ DB query performance, and ML queries (distance, k-NN/RAG); implemented in Rust and released as a library. Finds clear trade-offs: no single method dominates both space and query speed—some compressors yield higher compression but slower DB/ML query performance. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: 14242
Venue: VLDB
Year: 2025
Pagerank: 5.093636e-05
Overall Rank: 10,980 | 24.67%
DOI: 10.14778/3749646.3749701

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Kaisei Hishida (Keio University)
2. Chunwei Liu (Massachusetts Institute of Technology)
3. John Paparrizos (Aristotle University of Thessaloniki; Ohio State University)
4. Aaron J. Elmore (University of Chicago)

BibTeX Citation

@article{hishida_vldb25,
        title = {{Beyond Compression: A Comprehensive Evaluation of Lossless Floating-Point Compression}},
        author = {Hishida, Kaisei and Liu, Chunwei and Paparrizos, John and Elmore, Aaron J.},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {11},
        pages = {4396--4409},
        doi = {10.14778/3749646.3749701},
        url = {https://doi.org/10.14778/3749646.3749701},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 4 of 4 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,256	HYDRA: A Multi-Level Hierarchy-Driven Approach for Robust Anomaly Detection in Time Series	2026	SIGMOD	5.093636e-05
10,271	MUFASA: Fast and Accurate Multivariate Time-Series Clustering	2026	SIGMOD	5.093636e-05
10,298	The Power of Anomaly Detection in Predictive Maintenance: [Experiments & Analysis]	2026	SIGMOD	5.093636e-05
10,978	Time-Series Clustering: A Comprehensive Study of Data Mining, Machine Learning, and Deep Learning Methods	2025	VLDB	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 36 of 36 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
60	Integrating Compression and Execution in Column-Oriented Database Systems	2006	SIGMOD	0.0003955489
148	Gorilla: A Fast, Scalable, In-Memory Time Series Database	2015	VLDB	0.00029250767
870	BitWeaving: Fast Scans for Main Memory Data Processing	2013	SIGMOD	0.0001350293
1,364	Chimp: Efficient Lossless Floating Point Compression for Time Series Databases	2022	VLDB	0.00011020069
1,395	Column-oriented Database Systems	2009	VLDB	0.00010928358
1,579	k-Shape: Efficient and Accurate Clustering of Time Series	2015	SIGMOD	0.00010305183
1,761	ByteSlice: Pushing the Envelop of Main Memory Data Processing with a New Storage Layout	2015	SIGMOD	9.8154969e-05
1,805	SAND: Streaming Subsequence Anomaly Detection	2021	VLDB	9.7116108e-05
2,004	TSB-UAD: An End-to-End Benchmark Suite for Univariate Time-Series Anomaly Detection	2022	VLDB	9.3207067e-05
2,023	Decomposed Bounded Floats for Fast Compression and Queries	2021	VLDB	9.2950046e-05
2,788	BtrBlocks: Efficient Columnar Compression for Data Lakes	2023	SIGMOD	8.1205155e-05
3,269	ALP: Adaptive Lossless floating-Point Compression	2023	SIGMOD	7.5809516e-05
3,447	Volume Under the Surface: A New Accuracy Evaluation Measure for Time-Series Anomaly Detection	2022	VLDB	7.4085215e-05
3,540	Elf: Erasing-based Lossless Floating-Point Compression	2023	VLDB	7.3282654e-05
3,592	The FastLanes Compression Layout: Decoding >100 Billion Integers per Second with Scalar Code	2023	VLDB	7.2774889e-05
3,987	Choose Wisely: An Extensive Evaluation of Model Selection for Anomaly Detection in Time Series	2023	VLDB	6.9722766e-05
4,144	Tile-based Lightweight Integer Compression in GPU	2022	SIGMOD	6.8744592e-05
4,234	GRAIL: Efficient Time-Series Representation Learning	2019	VLDB	6.8171563e-05
4,604	Debunking Four Long-Standing Misconceptions of Time-Series Distance Measures	2020	SIGMOD	6.6104585e-05
5,037	A Deep Dive into Common Open Formats for Analytical DBMSs	2023	VLDB	6.3914026e-05
5,622	Good to the Last Bit: Data-Driven Encoding with CodecDB	2021	SIGMOD	6.1461066e-05
6,061	VergeDB: A Database for IoT Analytics on Edge Devices	2021	CIDR	5.9910733e-05
6,590	MOST: Model-Based Compression with Outlier Storage for Time Series Data	2023	SIGMOD	5.8316635e-05
7,173	CompressDB: Enabling Efficient Compressed Data Direct Processing for Various Databases	2022	SIGMOD	5.6830655e-05
7,890	FCBench: Cross-Domain Benchmarking of Lossless Compression for Floating-Point Data	2024	VLDB	5.521314e-05
8,000	PIDS: Attribute Decomposition for Improved Compression and Query Performance in Columnar Storage	2020	VLDB	5.5092344e-05
9,448	Theseus: Navigating the Labyrinth of Time-Series Anomaly Detection	2022	VLDB	5.2665425e-05
9,477	Odyssey: An Engine Enabling The Time-Series Clustering Journey	2023	VLDB	5.2634238e-05
9,733	SPARTAN: Data-Adaptive Symbolic Time-Series Approximation	2025	SIGMOD	5.227679e-05
10,747	A Structured Study of Multivariate Time-Series Distance Measures	2025	SIGMOD	5.093636e-05
10,961	BURST: Rendering Clustering Techniques Suitable for Evolving Streams	2025	VLDB	5.093636e-05
10,977	TSB-AutoAD: Towards Automated Solutions for Time-Series Anomaly Detection	2025	VLDB	5.093636e-05
10,978	Time-Series Clustering: A Comprehensive Study of Data Mining, Machine Learning, and Deep Learning Methods	2025	VLDB	5.093636e-05
11,300	Time-Series Anomaly Detection: Overview and New Trends	2024	VLDB	5.093636e-05
11,435	Accelerating Similarity Search for Elastic Measures: A Study and New Generalization of Lower Bounding Distances	2023	VLDB	5.093636e-05
13,463	SAND in Action: Subsequence Anomaly Detection for Streams	2021	VLDB	-

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	10,464	Improving LZ4 for Effective Compression and Efficient Query	2026	SIGMOD
2	2,519	Similarity search in the blink of an eye with compressed indices	2023	VLDB
3	921	Query Optimization In Compressed Database Systems	2001	SIGMOD
4	9,518	Revisiting B-tree Compression: An Experimental Study	2024	SIGMOD
5	3,949	A New Compression Method with Fast Searching on Large Databases	1987	VLDB
6	7,173	CompressDB: Enabling Efficient Compressed Data Direct Processing for Various Databases	2022	SIGMOD
7	9,520	Experimental Analysis of Large-scale Learnable Vector Storage Compression	2024	VLDB
8	2,023	Decomposed Bounded Floats for Fast Compression and Queries	2021	VLDB
9	7,890	FCBench: Cross-Domain Benchmarking of Lossless Compression for Floating-Point Data	2024	VLDB
10	11,770	An Evaluation of Methods of Compressing Doubles	2020	SIGMOD